Lune

EMNLP Findings2022

Knowledge-augmented Self-training of A Question Rewriter for Conversational Knowledge Base Question Answering

Xirui Ke, Jing Zhang, Xin Lv, Yiqi Xu, Shulin Cao, Cuiping Li, Hong Chen, Juanzi Li

Abstract

The recent rise of conversational applications such as online customer service systems and intelligent personal assistants has promoted the development of conversational knowledge base question answering (ConvKBQA). Different from the traditional single-turn KBQA, ConvKBQA usually explores multi-turn questions around a topic, where ellipsis and coreference pose great challenges to the single-turn KBQA systems which require self-contained questions. In this paper, we propose a rewriteand-reason framework to first produce a fullfledged rewritten question based on the conversation history and then reason the answer by existing single-turn KBQA models. To overcome the absence of the rewritten supervision signals, we introduce a knowledge-augmented self-training mechanism to transfer the question rewriter from another dataset to adapt to the current knowledge base. Our question rewriter is decoupled from the subsequent QA process, which makes it easy to be united with either retrieval-based or semantic parsing-based KBQA models. Experiment results demonstrate the effectiveness of our method and a new state-of-the-art result is achieved. The code and dataset are available online now 1 .

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

1 top-tier paper has cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • RNG-KBQA: Generation Augmented Iterative Ranking for Knowledge Base Question Answering cites SPARQA: Skeleton-Based Semantic Parsing for Complex Questions over Knowledge Bases
  • Beyond I.I.D.: Three Levels of Generalization for Question Answering on Knowledge Bases cites SPARQA: Skeleton-Based Semantic Parsing for Complex Questions over Knowledge Bases
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers1

  1. Explainable Conversational Question Answering over Heterogeneous Sources via Iterative Graph Neural NetworksPhilipp Christmann, Rishiraj Saha Roy, Gerhard WeikumSIGIR 2023 · 21 citations

Builds on13

  1. Confidence Regularized Self-TrainingYang Zou, Zhiding Yu, Xiaofeng Liu, B. V. K. Vijaya Kumar et al.ICCV 2019 · 901 citations
  2. Beyond I.I.D.: Three Levels of Generalization for Question Answering on Knowledge BasesYu Gu, Sue Kase, Michelle Vanni, Brian M. Sadler et al.WWW 2021 · 304 citations
  3. RNG-KBQA: Generation Augmented Iterative Ranking for Knowledge Base Question AnsweringXi Ye, Semih Yavuz, Kazuma Hashimoto, Yingbo Zhou et al.ACL 2022 · 203 citations
  4. Uncertainty-aware Self-training for Few-shot Text ClassificationSubhabrata Mukherjee, Ahmed Hassan AwadallahNeurIPS 2020 · 182 citations
  5. SPARQA: Skeleton-Based Semantic Parsing for Complex Questions over Knowledge BasesYawei Sun, Lingling Zhang, Gong Cheng, Yuzhong QuAAAI 2020 · 143 citations

Related papers

  1. Conversational Question Answering with Language Models Generated Reformulations over Knowledge GraphLihui Liu, Blaine Hill, Boxin Du, Fei Wang et al.ACL Findings 2024 · 12 citations
  2. CoTKR: Chain-of-Thought Enhanced Knowledge Rewriting for Complex Knowledge Graph Question AnsweringYike Wu, Yi Huang, Nan Hu, Yuncheng Hua et al.EMNLP 2024 · 9 citations
  3. CONQRR: Conversational Query Rewriting for Retrieval with Reinforcement LearningZeqiu Wu, Yi Luan, Hannah Rashkin, David Reitter et al.EMNLP 2022 · 37 citations
  4. ChatKBQA: A Generate-then-Retrieve Framework for Knowledge Base Question Answering with Fine-tuned Large Language ModelsHaoran Luo, Haihong E, Zichen Tang, Shiyao Peng et al.ACL Findings 2024 · 88 citations
  5. Learn to Resolve Conversational Dependency: A Consistency Training Framework for Conversational Question AnsweringGangwoo Kim, Hyunjae Kim, Jungsoo Park, Jaewoo KangACL 2021
Dusk over the sea between two cliffs drawn in fine vertical lines